1
|
Vališ J, Fousková M, Janstová D, Habartová L, Petrtýl J, Petruželka L, Synytsya A, Setnička V. Automated classification pipeline for real-time in vivo examination of colorectal tissue using Raman spectroscopy. Spectrochim Acta A Mol Biomol Spectrosc 2024; 313:124152. [PMID: 38503254 DOI: 10.1016/j.saa.2024.124152] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/11/2024] [Revised: 03/07/2024] [Accepted: 03/11/2024] [Indexed: 03/21/2024]
Abstract
Colorectal cancer is the third most common malignancy worldwide and one of the leading causes of death in oncological patients with its diagnosis typically involving confirmation by tissue biopsy. In vivo Raman spectroscopy, an experimental diagnostic method less invasive than a biopsy, has shown great potential to discriminate between normal and cancerous tissue. However, the complex and often manual processing of Raman spectra along with the absence of a suitable instant classifier are the main obstacles to its adoption in clinical practice. This study aims to address these issues by developing a real-time automated classification pipeline coupled with a user-friendly application tailored for non-spectroscopists. First, in addition to routine colonoscopy, 377 subjects underwent in vivo acquisitions of Raman spectra of healthy tissue, adenomatous polyps, or cancerous tissue, which were conducted using a custom-made microprobe. The spectra were then loaded into the pipeline and pre-processed in several steps, including standard normal variate transformation and finite impulse response filtration. The quality of the pre-processed spectral data was checked based on their signal-to-noise ratio before the suitable spectra were decomposed and classified using a combination of principal component analysis and a support vector machine, respectively. After five-fold cross-validation, the developed classifier exhibited 100% sensitivity toward adenocarcinoma and adenomatous polyps. The overall accuracy was 96.9% and 79.2% for adenocarcinoma and adenomatous polyps respectively. In addition, an application with a graphical user interface was developed to facilitate the use of our data pipeline by medical professionals in a clinical environment. Overall, the combination of supervised and unsupervised machine learning with algorithmic pre-processing of in vivo Raman spectra appears to be a viable way of reducing the relatively large number of biopsies currently needed to definitively diagnose colorectal cancer.
Collapse
Affiliation(s)
- Jan Vališ
- Department of Analytical Chemistry, Faculty of Chemical Engineering, University of Chemistry and Technology, Prague, Technická 5, 166 28 Prague 6, Czech Republic
| | - Markéta Fousková
- Department of Analytical Chemistry, Faculty of Chemical Engineering, University of Chemistry and Technology, Prague, Technická 5, 166 28 Prague 6, Czech Republic
| | - Daniela Janstová
- Department of Analytical Chemistry, Faculty of Chemical Engineering, University of Chemistry and Technology, Prague, Technická 5, 166 28 Prague 6, Czech Republic
| | - Lucie Habartová
- Department of Analytical Chemistry, Faculty of Chemical Engineering, University of Chemistry and Technology, Prague, Technická 5, 166 28 Prague 6, Czech Republic
| | - Jaromír Petrtýl
- 4(th) Department of Internal Medicine, General University Hospital in Prague and 1(St) Faculty of Medicine, Charles University in Prague, U Nemocnice 2, 128 08 Prague 2, Czech Republic
| | - Luboš Petruželka
- Department of Oncology, General University Hospital in Prague and 1(St) Faculty of Medicine, Charles University in Prague, U Nemocnice 2, 128 08 Prague 2, Czech Republic
| | - Alla Synytsya
- Department of Analytical Chemistry, Faculty of Chemical Engineering, University of Chemistry and Technology, Prague, Technická 5, 166 28 Prague 6, Czech Republic
| | - Vladimír Setnička
- Department of Analytical Chemistry, Faculty of Chemical Engineering, University of Chemistry and Technology, Prague, Technická 5, 166 28 Prague 6, Czech Republic.
| |
Collapse
|
2
|
Synytsya A, Janstová D, Šmidová M, Synytsya A, Petrtýl J. Evaluation of IR and Raman spectroscopic markers of human collagens: Insides for indicating colorectal carcinogenesis. Spectrochim Acta A Mol Biomol Spectrosc 2023; 296:122664. [PMID: 36996519 DOI: 10.1016/j.saa.2023.122664] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/27/2022] [Revised: 02/26/2023] [Accepted: 03/21/2023] [Indexed: 06/19/2023]
Abstract
Vibrational spectroscopic methods are widely used in the molecular diagnostics of carcinogenesis. Collagen, a component of connective tissue, plays a special role as a biochemical marker of pathological changes in tissues. The vibrational bands of collagens are very promising to distinguish between normal colon tissue, benign and malignant colon polyps. Differences in these bands indicate changes in the amount, structure, conformation and the ratio between the individual structural forms (subtypes) of this protein. The screening of specific collagen markers of colorectal carcinogenesis was carried out based on the FTIR and Raman (λex 785 nm) spectra of colon tissue samples and purified human collagens. It was found that individual types of human collagens showed significant differences in their vibrational spectra, and specific spectral markers were found for them. These collagen bands were assigned to specific vibrations in the polypeptide backbone, amino acid side chains and carbohydrate moieties. The corresponding spectral regions for colon tissues and colon polyps were investigated for the contribution of collagen vibrations. Mentioned spectral differences in collagen spectroscopic markers could be of interest for early ex vivo diagnosis of colorectal carcinoma if combine vibrational spectroscopy and colonoscopy.
Collapse
Affiliation(s)
- Alla Synytsya
- Department of Analytical Chemistry, University of Chemistry and Technology Prague, Technická 5, 166 28 Prague 6, Czech Republic.
| | - Daniela Janstová
- Department of Analytical Chemistry, University of Chemistry and Technology Prague, Technická 5, 166 28 Prague 6, Czech Republic
| | - Miroslava Šmidová
- Department of Analytical Chemistry, University of Chemistry and Technology Prague, Technická 5, 166 28 Prague 6, Czech Republic
| | - Andriy Synytsya
- Department of Carbohydrates and Cereals, University of Chemistry and Technology Prague, Technická 5, 166 28 Prague 6, Czech Republic
| | - Jaromír Petrtýl
- 4th Internal Clinic-Gastroenterology and Hepatology, 1(st) Faculty of Medicine, Charles University in Prague and General University Hospital in Prague, U Nemocnice 2, 128 00 Prague 2, Czech Republic
| |
Collapse
|
3
|
Abstract
Some antibiotics and synthetic inhibitors affect, in several ways, the life cycle of Neurospora crassa (germination of conidia leads to myceliar growth leads to formation of conidia). Bikaverin, cyanein, scopathricin and phenethyl alcohol retard the germination of conidia, without inhibiting it completely. 5-Fluorouracil, ramihyphin A and zygosporin A (cytochalasin D) do not inhibit the germination. Bikaverin brings about a thickening of the hyphae of growing mycelium. Ramihyphin A, cyanein, scopathricin and zygosporin A stimulate the ramification of hyphae while 5-fluorouracil and phenethyl alcohol do not affect the myceliar morphology apart from their inhibitory effect on growth. Actinomycin D, 5-fluorouracil, cycloheximide, ramihyphin A and partially also sodium iodoacetate inhibit to a different degree the photoinduced formation of conidia. The inhibition by 5-fluorouracil is very conspicuous when the agent is present during the photoinduction but considerably weaker when it is applied 2 h after the photoinduction.
Collapse
|